Data fusion method and system for quality safety traceability of pearlescent material production

Abstract

The present application relates to the technical field of quality traceability of pearl material production, and particularly relates to a data fusion method and system for quality and safety traceability of pearl material production. The method comprises the following steps: obtaining pearl material production whole process data, determining initial properties of pearl raw materials in combination with production workshop running states; analyzing dynamic fatigue growth trend based on production equipment running data, and evaluating equipment coupling degradation states in combination with raw material properties; monitoring product dynamic stability based on degradation states; evaluating product deterioration trend and detecting product quality and safety risks through packaging and transportation simulation; finally, fusing product quality and safety data and stability data, identifying production process defects, completing optimized processing of whole process data, and obtaining optimized data which can be used for process tracing and adjustment; the present application realizes more perfect pearl material production quality through pearl material production quality traceability.

Description

Technical Field

[0001] This invention relates to the field of pearlescent material production quality traceability technology, and in particular to a data fusion method and system for traceability of pearlescent material production quality and safety. Background Technology

[0002] Pearlescent materials, as functional materials with unique optical effects, are widely used in coatings, cosmetics, plastics, printing inks, and other fields. Due to their primary applications in visual presentation, human contact, and high-end decoration, the quality stability and safety of pearlescent materials have become a key focus of the industry. The quality of pearlescent materials is affected by multiple factors, including the composition of impurities in raw materials, particle size distribution, surface coating stability, production equipment operating status, workshop environmental parameters, and the sealing of packaging structures. In actual production, issues such as high impurity content in raw materials, oxidation and decomposition of the coating layer, particle agglomeration, coupling attenuation of production equipment, operating frequency drift, or damage to packaging structures can lead to increased irritation, decreased stability, and even deterioration of the finished product. However, traditional methods for tracing the quality and safety of pearlescent materials suffer from inaccuracies in monitoring the dynamic stability of finished products and inaccurate quality and safety testing. Summary of the Invention

[0003] Therefore, it is necessary to provide a data fusion method and system for tracing the quality and safety of pearlescent material production in order to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a data fusion method for quality and safety traceability in pearlescent material production includes the following steps:

[0005] Step S1: Obtain data on the entire pearlescent material production process; collect data from the pearlescent material production workshop based on the data from the entire pearlescent material production process; determine the initial property data of the pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the entire pearlescent material production process.

[0006] Step S2: Determine the dynamic fatigue growth trend of the material production equipment based on the data from the pearlescent material production workshop; determine the coupled degradation status of the material production equipment based on the initial property data of the pearlescent raw materials and the dynamic fatigue growth trend of the material production equipment; monitor the dynamic stability properties of the finished pearlescent material based on the coupled degradation status of the material production equipment.

[0007] Step S3: Based on the full-process data of pearlescent material production, simulate the packaging and transportation of the finished pearlescent material to obtain the packaging and transportation simulation data; monitor the deterioration trend of the finished pearlescent material based on the packaging and transportation simulation data; and detect the quality and safety data of the finished pearlescent material based on the deterioration trend.

[0008] Step S4: Based on the quality and safety data of pearlescent materials and the dynamic stability data of finished pearlescent materials, assess the defect data of the pearlescent material production process; based on the defect data of the pearlescent material production process, optimize the production process data of the entire pearlescent material production process to obtain optimized pearlescent material production process data.

[0009] This invention improves the accuracy of identifying the initial properties of raw materials by integrating data from the entire pearlescent material production process with production workshop data, thereby strengthening the controllability of material quality from the source. By combining workshop data with equipment fatigue growth trends, it effectively assesses equipment coupling degradation, enhances the dynamic perception of equipment operating status, and ensures production continuity and product consistency. Based on the dynamic stability of finished products, it conducts packaging and transportation simulations to identify the impact of packaging structure on product performance in advance, ensuring product stability and quality safety during transportation. Through the fusion of deterioration trend and quality safety data, it deeply explores potential defects in production, improving the accuracy and response speed of quality traceability. Furthermore, it utilizes defect data to optimize the entire process data, constructing a data closed-loop mechanism to enhance the flexibility and efficiency of the production process, achieving full-process quality and safety traceability and intelligent optimization of the production process, thus enhancing the stability, reliability, and safety of the pearlescent material production system. Therefore, this invention is an optimization of the traditional traceability system for the production quality and safety of pearlescent materials. It solves the problems of inaccurate monitoring of the dynamic stability of finished pearlescent materials and inaccurate quality and safety testing of pearlescent materials in the traditional traceability system, and improves the accuracy of monitoring the dynamic stability of finished pearlescent materials and the accuracy of quality and safety testing of pearlescent materials.

[0010] This invention also provides a data fusion system for quality and safety traceability in pearlescent material production, used to execute the data fusion method for quality and safety traceability in pearlescent material production as described above. The data fusion system for quality and safety traceability in pearlescent material production includes:

[0011] The raw material initial property determination module is used to acquire data from the entire pearlescent material production process; collect data from the pearlescent material production workshop based on the data from the entire pearlescent material production process; and determine the initial property data of pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the entire pearlescent material production process.

[0012] The finished product dynamic stability monitoring module is used to determine the dynamic fatigue growth trend of the material production equipment based on data from the pearlescent material production workshop; to determine the coupled degradation status of the material production equipment based on the initial property data of the pearlescent raw materials and the dynamic fatigue growth trend of the material production equipment; and to monitor the dynamic stability properties of the finished pearlescent material based on the coupled degradation status of the material production equipment.

[0013] The pearlescent material quality and safety testing module is used to simulate the dynamic stability of finished pearlescent materials based on data from the entire pearlescent material production process, thereby obtaining pearlescent material packaging and transportation simulation data; to monitor the deterioration trend of finished pearlescent materials based on the pearlescent material packaging and transportation simulation data; and to detect the quality and safety data of pearlescent materials based on the deterioration trend of finished pearlescent materials.

[0014] The production process optimization module is used to evaluate the production process defects of pearlescent materials based on the quality and safety data of pearlescent materials and the dynamic stability of finished pearlescent materials; and to optimize the entire production process data of pearlescent materials based on the production process defect data to obtain optimized production process data of pearlescent materials.

[0015] The present invention relates to a data fusion system for quality and safety traceability in pearlescent material production. This system can implement any data fusion method for quality and safety traceability in pearlescent material production, and is used to combine the operation and signal transmission medium between various modules to complete the data fusion method for quality and safety traceability in pearlescent material production. The modules within the system cooperate with each other to accurately trace the quality of pearlescent materials from raw materials to finished products and to optimize production intelligently, thereby improving product stability and production safety. Attached Figure Description

[0016] Figure 1 A flowchart illustrating the steps of a data fusion method for tracing the quality and safety of pearlescent material production.

[0017] Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S3.

[0018] Figure 3 This is a schematic diagram of the detection of coupling degradation status of production equipment in this invention;

[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0021] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0022] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0023] To achieve the above objectives, please refer to Figures 1 to 3 A data fusion method for tracing the quality and safety of pearlescent material production includes the following steps:

[0024] Step S1: Obtain data on the entire pearlescent material production process; collect data from the pearlescent material production workshop based on the data from the entire pearlescent material production process; determine the initial property data of the pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the entire pearlescent material production process.

[0025] In this embodiment of the invention, during the production of pearlescent materials, data from the entire production process is acquired through an industrial data acquisition system deployed by the manufacturing enterprise at each stage of production. This data includes, but is not limited to, raw material batch information, feeding time, stirring speed, heating temperature, drying time, surface treatment process number, quality inspection results, and process alarm records. The data is uniformly recorded in a Time Series Database (TSDB) format. Subsequently, in conjunction with a workshop environmental monitoring system configured on the production line, data from the pearlescent material production workshop is collected. This data includes indicators such as temperature and humidity, air cleanliness, particle concentration, electrostatic potential change, motor current, and equipment switching frequency at each production stage (e.g., mixing, coating, drying). This data is collected using the Modbus protocol to a unified edge acquisition terminal and transmitted to the central data platform via the OPC UA interface. Then, by establishing data fusion processing logic, the aforementioned workshop data is correlated and paired with the entire process parameters. Specifically, the batch numbers and warehousing times of rutile titanium dioxide in the pearlescent raw material data were compared using timestamps. Combined with variations in workshop temperature ranges and electrostatic levels, the activity evolution of the raw materials under actual environmental conditions was analyzed. Furthermore, characterization parameters such as moisture content, pH value, and specific surface area of ​​the raw materials were segmented and calibrated using workshop operating status data corresponding to the production time points, forming an initial property dataset for pearlescent raw materials. This dataset includes the initial particle size distribution, surface potential energy level, and potential agglomeration trend indicators, providing fundamental support for subsequent equipment status and finished product performance analysis.

[0026] Step S2: Determine the dynamic fatigue growth trend of the material production equipment based on the data from the pearlescent material production workshop; determine the coupled degradation status of the material production equipment based on the initial property data of the pearlescent raw materials and the dynamic fatigue growth trend of the material production equipment; monitor the dynamic stability properties of the finished pearlescent material based on the coupled degradation status of the material production equipment.

[0027] In this embodiment of the invention, based on the aforementioned collected data from the pearlescent material production workshop, the operation logs of each key processing equipment in the workshop are structurally parsed. Fields such as switch status, frequency adjustment commands, speed changes, and load current in the log text are normalized in a time-axis manner to form the pearlescent material production workshop operation sequence data. Subsequently, by constructing a workshop operation intensity monitoring model, the frequency of various operation commands and the concurrent operation rate of equipment per unit time are statistically analyzed, and the workshop production intensity fluctuation curve is calculated accordingly. This curve is calculated by taking the mean and variance of the difference in operation intensity between adjacent time periods and extracting its upward slope. When the slope exceeds 0.87 for three consecutive cycles, the workshop is determined to be in a high-intensity pressure operation state. At the same time, combined with the collaborative operation relationship between equipment, a Pearson correlation coefficient matrix is ​​constructed to perform correlation analysis on the load change trends of multiple devices in the same production line to obtain coupled operation interference data. The above-mentioned high-intensity fluctuations and coupled interference risks are integrated to form the dynamic fatigue growth trend of material production equipment. Next, particle size distribution and moisture content data from the initial properties of the pearlescent raw materials were retrieved to establish a physical dispersion resistance calculation model, predicting the viscous forces that the raw material slurry needs to overcome during the mixing stage. Based on this viscous force trend, the torque load growth process of the mixing system was deduced. Combined with real-time torque acquisition data and stress sensor data from the mixing equipment, abnormal fluctuations in the equipment's shear stress were monitored. Simultaneously, based on the rotational speed fluctuation data obtained from the angular velocity sensors deployed in the equipment's transmission system, and combined with the upward trend of the viscous load, the growth process of torque fluctuation frequency and intensity was derived, thereby comprehensively estimating the equipment coupling degradation status. Finally, based on the equipment coupling degradation status, the dynamic stability of the finished pearlescent material was monitored. Specifically, after drying, the particle size deviation of the finished product was monitored in real time using an online particle size analyzer (such as a laser particle size analyzer), and combined with the color difference data collected by an online colorimeter, a particle size deviation-color difference drift response model was established. When the average particle size deviation is greater than ±0.15μm or the color difference ΔE is greater than 1.2, the dynamic stability of the finished product is determined to have fluctuated significantly.

[0028] Step S3: Based on the full-process data of pearlescent material production, simulate the packaging and transportation of the finished pearlescent material to obtain the packaging and transportation simulation data; monitor the deterioration trend of the finished pearlescent material based on the packaging and transportation simulation data; and detect the quality and safety data of the finished pearlescent material based on the deterioration trend.

[0029] In this embodiment of the invention, after monitoring the dynamic stability of the finished product, a multi-factor simulation model of the pearlescent material packaging and transportation process is constructed based on the data of the entire pearlescent material production process and the physical properties of the finished product. This model considers the mechanical vibration frequency (10200Hz), peak vehicle acceleration (up to 5g), air pressure fluctuations (10101kPa), and environmental humidity changes (30%~95%RH) during transportation. Using finite element analysis, the stress distribution and structural deformation of the pearlescent material under different packaging structures (such as single-layer plastic sealing + cardboard box, double-layer aluminum film composite packaging) are simulated, forming simulation data for pearlescent material packaging and transportation. Based on the above simulation data, time-domain analysis is performed on the changes in packaging sealing performance, calculating the rate of decrease in packaging structure sealing parameters (such as a permeability change rate exceeding 0.03g / m²·d), and determining the risk level of packaging structure damage. Subsequently, by combining the trends in particle size and color difference changes in the dynamic stability of the finished product, the material degradation process under damage conditions was estimated, including: increased oxidation rate of the surface coating layer due to air penetration induced by packaging damage (>0.05 mg / cm²·d), decreased material adhesion induced by moisture penetration, and increased probability of microbial proliferation. Then, based on the weighted fusion of various risk factors, a degradation trend prediction curve was constructed, and the safety performance degradation threshold of the material at different time points was extracted, forming pearlescent material quality and safety data, covering failure mode classification (oxidation type, moisture type, infection type) and time-performance degradation relationship.

[0030] Step S4: Based on the quality and safety data of pearlescent materials and the dynamic stability data of finished pearlescent materials, assess the defect data of the pearlescent material production process; based on the defect data of the pearlescent material production process, optimize the production process data of the entire pearlescent material production process to obtain optimized pearlescent material production process data.

[0031] In this embodiment of the invention, after obtaining the quality and safety data of pearlescent materials, it is fused with the dynamic stability properties of the finished product at the field level. Specifically, this involves matching and aligning the particle size change rate, oxidation decomposition trend curve, and packaging damage index from the quality and safety data with the particle size deviation, color difference fluctuation amplitude, and stirring viscosity change rate from the dynamic stability data. A unified material behavior trajectory is then constructed using a DTW (Dynamic Time Warping) algorithm. Subsequently, based on the behavior trajectory data, backtracking is performed, and correlation mining is conducted using process parameters throughout the entire process (such as drying temperature, mixing time, stirring rate, equipment start-up and shutdown frequency, etc.). The probability of failure events occurring under different time periods and equipment operating conditions is statistically analyzed to form traceability data for the entire pearlescent material production process. This traceability data identifies high-frequency defect patterns (such as the path of "high humidity batch - high slope operation - agglomeration") through cluster analysis, and outputs pearlescent material production process defect data accordingly. Finally, based on the defect data feedback to the entire process data management system, the key process parameter setting ranges are reconstructed to form a parameter optimization table based on a defect suppression mechanism. The system automatically generates adjustment suggestions, including reducing stirring intensity by 5-10%, increasing drying temperature by 3°C, and controlling workshop temperature within ±1.5°C, forming optimized data for the pearlescent material production process. This data is synchronously transmitted to the MES system as a basis for subsequent batch production control, achieving closed-loop optimization of quality and safety based on data fusion.

[0032] Preferably, step S1 includes the following steps:

[0033] Step S11: Obtain data on the entire pearlescent material production process;

[0034] In this embodiment of the invention, a unified industrial data acquisition architecture is set up in the pearlescent material manufacturing plant to acquire data throughout the entire production process. This architecture relies on PLC controllers, distributed data acquisition devices (such as Siemens S7-1200 and NI CompactDAQ), industrial cameras, environmental sensor nodes, RFID readers, and online data relay gateways to continuously collect various key data during the production process. The specific data collected includes, but is not limited to: raw material warehousing time, batch number, supplier code, transportation conditions (temperature, humidity, vibration data, etc.), raw material unloading time, storage area and conditions, sampling information, input ratio data, mixing uniformity parameters, real-time temperature and humidity records, production cycle time, operation duration, equipment operating status and alarm logs, as well as product composition ratios, packaging time, and test results. All the above data undergoes preliminary preprocessing through an edge computing module before being uploaded to a centralized database deployed on a local server or industrial cloud platform. The data is then standardized and archived according to unified timestamps, field naming, and data types, forming complete data for the entire pearlescent material production process.

[0035] Step S12: Collect pearlescent raw material data based on the entire pearlescent material production process;

[0036] In this embodiment of the invention, pearlescent raw material data is collected based on the acquired data of the entire pearlescent material production process. This step involves identifying the corresponding warehousing timestamp, supplier identification information, and batch number of the raw materials, and then filtering data fields related to the raw material warehousing and usage stages from the dataset. These include the physicochemical properties of the raw materials (such as particle size distribution range, type of surface modifier, heavy metal content detection data, pH value, water absorption rate, and surface potential), packaging conditions (sealing bag material, vacuum level), warehousing inspection reports (quantitative data generated by testing equipment such as laser particle size analyzer, ICP-MS spectrometer, and SEM scanning electron microscope), and timeline data such as the actual outbound time, feeding section number, and reaction vessel entry time recorded in the material flow sheet. All raw material data must be bound to the production data according to a unique batch code after collection to form a traceable raw material sub-database for subsequent steps.

[0037] Step S13: Collect data from the pearlescent material production workshop based on the entire pearlescent material production process data;

[0038] In this embodiment of the invention, during the data collection process in the pearlescent material production workshop, environmental monitoring devices (such as temperature and humidity sensors, wind speed and air volume recorders, and aerosol monitoring probes), production equipment status acquisition modules (including torque sensors, current and voltage sensors, vibration sensors, and shaft temperature sensors), and a video acquisition system deployed in key areas of the workshop are used to record the production conditions around the clock. Specific data collected includes: temperature change curves, humidity change records, and operating power, load changes, fault alarm frequencies, and shutdown records of key equipment such as stirring tanks and coating reactors in different work sections. Equipment operation logs are uploaded to a unified database in a standardized manner via the OPC-UA protocol, and time node corrections are performed using the task scheduling table in the MES system to ensure that workshop data matches raw material usage data and process data. Simultaneously, information such as the actual material feeding time, work group, and shift personnel ID recorded on the control panel is also stored synchronously to improve the boundary conditions for subsequent analysis.

[0039] Step S14: Determine the initial property data of pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the pearlescent raw materials.

[0040] In this embodiment of the invention, the pearlescent raw material data obtained in step S12 and the pearlescent material production workshop data obtained in step S13 are jointly analyzed to determine the properties of the raw materials in the initial stage. In practice, data fusion algorithms (such as multi-channel time series clustering and attribute cross-analysis) are used to perform feature-level fusion of the two types of data. The particle size data of the raw materials is compared with the temperature and humidity fluctuation data of the workshop to identify the coupling effect between the surface charge fluctuation of the material and environmental factors. Secondly, based on the impurity and heavy metal content in the raw materials, combined with the changes in stirring torque and pH value of the reactants recorded in the workshop, the sensitivity index of the catalytic oxidation reaction is analyzed. Then, by analyzing the locations where shear resistance fluctuations frequently occur during equipment operation in the workshop, and comparing them with the polymer chain breakage sensitivity index in the raw materials, the initial structural stability is inferred. The above analysis results are summarized as the initial property data of the pearlescent raw materials. This data includes, but is not limited to: reaction catalytic oxidation sensitivity index, electrostatic repulsion decrease value, impurity critical threshold, angle of repose fluctuation, particle size drift probability index, etc. These data will be used as input conditions to flow into the subsequent equipment dynamic fatigue and product dynamic stability analysis modules to ensure a complete closed loop of the data chain.

[0041] Preferably, step S14 includes the following steps:

[0042] Step S141: Detect the impurity content of pearlescent raw materials to obtain impurity content data of pearlescent raw materials;

[0043] In this embodiment of the invention, the detection of impurity content in pearlescent raw materials involves pretreatment of the raw material sample (such as acid digestion using a fully automated digester) followed by component analysis using an inductively coupled plasma optical emission spectrometer (ICP-OES) and a gas chromatography-mass spectrometer (GC-MS). During this process, the detection targets are inorganic impurities (such as oxides of silicon, calcium, aluminum, and iron) and organic impurities (such as residual reaction byproducts and monomer residues). The mass fraction of each type of impurity is calculated using a standard curve method, and the data are uniformly collected in ppm to generate pearlescent raw material impurity content data.

[0044] Step S142: Determine the heavy metal content data of pearlescent raw materials based on the impurity content data of the pearlescent raw materials;

[0045] In this embodiment of the invention, heavy metal-related elements (such as Pb, Cd, Cr, Hg, As, Ni, Cu, Zn, etc.) are screened from the impurity component content data obtained in step S141, and the data for each element are categorized and summarized. Specifically, the contents of Pb, Cd, etc., are summarized separately according to raw material batch, arrival time, and sampling point to ensure batch traceability consistency. The heavy metal content data are presented in a structured data table in the form of element name + mass fraction, serving as input for subsequent analysis.

[0046] Step S143: Based on the heavy metal content data of pearlescent raw materials, perform catalytic oxidation analysis on the pearlescent raw material data to obtain the catalytic oxidation status of the pearlescent raw material reaction;

[0047] In this embodiment of the invention, a constant-temperature reactor (set temperature 80°C, stirring speed 600 rpm) was used in conjunction with an online oxidation-reduction potential (ORP) detection module and a UV-Vis spectrophotometer to analyze the catalytic oxidation reaction behavior of pearlescent raw materials in the presence of hydrogen peroxide. During the measurement process, the oxidation potential change curve, hydrogen peroxide decomposition rate, and formation of active intermediates were recorded. Combined with the heavy metal content data in the pearlescent raw materials, the degree of involvement of metal ions in the catalytic reaction process was evaluated. Based on the activity change characteristics at reaction time points, parameters of the catalytic oxidation status of the pearlescent raw materials were obtained, including the initial reaction rate, the length of the reaction stabilization period, and the maximum ORP change.

[0048] Step S144: Detect the surface charge change trend of pearlescent raw materials based on the data of pearlescent raw materials;

[0049] In this embodiment of the invention, a Zeta potential analyzer (such as the Malvern Zetasizer Ultra) was used to detect the surface charge characteristics of pearlescent raw material particles in buffer solutions with different pH values. The raw material samples were ultrasonically dispersed in a standard dispersion medium for 5 minutes before testing, and their Zeta potential distribution curves were recorded within the pH range of 3–11. The detection results were used to analyze their charging trend and stability, with particular attention paid to the decreasing trend of the absolute value of the Zeta potential and the shift in the isoelectric point position, serving as the core basis for data on the surface charge change trend of the pearlescent raw material.

[0050] Step S145: Measure the temperature change trend in the pearlescent material production workshop based on data from the pearlescent material production workshop;

[0051] In this embodiment of the invention, the temperature change trend in the pearlescent material production workshop is collected in real time by a distributed industrial temperature and humidity sensor node network. Honeywell HIH series sensors are selected and installed at key locations such as the reactor inlet / outlet, feeding platform, above the drying section conveyor line, and next to the stirring system. The sampling frequency is set to 5 seconds / time. After the data is uploaded to the local OPC server, a time-series analysis algorithm is used to extract the mean, fluctuation amplitude, maximum gradient, and trend inflection point positions from the temperature curve, generating temperature change trend data for the pearlescent material production workshop.

[0052] Step S146: When the temperature change trend in the pearlescent material production workshop exceeds ±3.2°C, determine the decrease in electrostatic repulsion of raw material particles based on the surface charge change trend of the pearlescent raw materials.

[0053] In this embodiment of the invention, the surface charge change trend data obtained in step S144 and the workshop temperature change trend data obtained in step S145 are jointly analyzed. The focus is on the ±3.2°C threshold in the temperature change trend, and a judgment is made based on whether the decrease in Zeta potential within 5 minutes before and after the temperature exceeds this threshold is greater than 15%. When the condition is met, the electrostatic repulsion decrease index is calculated, and the decrease in electrostatic repulsion of the raw material particles is confirmed in conjunction with the change in particle size distribution.

[0054] Step S147: Estimate the spontaneous agglomeration status of pearlescent raw materials based on the decrease in electrostatic repulsion of raw material particles;

[0055] In this embodiment of the invention, based on the confirmed decrease in electrostatic repulsion, the agglomeration trend of the raw materials under static conditions is further measured. Specifically, the sample is placed in a transparent cuvette, and the changes in light intensity distribution within 0-30 minutes are recorded using a light scattering imaging system (such as Turbiscan Lab). The agglomeration rate and agglomerate particle size growth rate are quantified by the increasing trend of bottom scattered light intensity and the increasing light transmittance of the top clear liquid. The spontaneous agglomeration status data of the pearlescent raw materials are output in the form of average agglomeration rate μg / min and volume distribution shift index.

[0056] Step S148: Determine the initial property data of pearlescent raw materials based on the spontaneous agglomeration status and the catalytic oxidation status of pearlescent raw materials.

[0057] In this embodiment of the invention, the catalytic oxidation status of pearlescent raw materials obtained in step S143 and the spontaneous agglomeration status data obtained in step S147 are fused and analyzed. The attribute weighting ratio analysis method is used to standardize and weighted average the two sets of indicators, outputting the initial property data of the pearlescent raw materials. This data includes indicators such as reaction sensitivity score, particle size drift index, repulsion reduction risk coefficient, and agglomeration rate level, forming a set of structured initial property description fields, which serve as the data basis for subsequent equipment degradation analysis and product stability assessment.

[0058] Preferably, step S2, determining the dynamic fatigue growth trend of the material production equipment based on data from the pearlescent material production workshop, includes:

[0059] The structural complexity of the pearlescent material production workshop was determined based on data from the workshop.

[0060] In this embodiment of the invention, the structural complexity of a pearlescent material production workshop is quantitatively analyzed based on Building Information Modeling (BIM) data, sensor deployment maps, and workstation functional structure diagrams. Structural complexity parameters are derived by calculating indicators such as workshop spatial distribution density, the number of connection nodes for key equipment, and the workstation functional coupling index. Specific methods include: using 3D point cloud reconstruction technology to scan and model the workshop space; extracting connection paths, functional chains, and redundancy of operational processes from the workshop process flow diagram; and representing structural complexity using the Structural Coupling Index (SCI), with a value range of 0 to 1, where a higher value indicates a more complex structure.

[0061] Extract the pearlescent material production workshop operation log from the pearlescent material production workshop data;

[0062] In this embodiment of the invention, industrial internet data acquisition nodes (such as OPC UA communication interfaces) are used to extract the operation logs of the pearlescent material production workshop. The logs include equipment start-up and shutdown records, temperature and pressure alarm information, material feeding times, maintenance cycles, and downtime reasons. A timestamp alignment mechanism is set during the data acquisition process to ensure millisecond-level time accuracy of the log data. Real-time acquisition and unified storage are performed using a Kafka message queue system. After preprocessing to remove duplicates, invalid entries, and incorrectly formatted items, the raw log data enters the time-series analysis stage.

[0063] Time-series analysis was performed on the operation log of the pearlescent material production workshop to obtain time-series data of the pearlescent material production workshop.

[0064] In this embodiment of the invention, a multi-scale feature extraction method based on a sliding window mechanism is used to model the workshop operation logs for time series analysis. The window width is set to 30 minutes and the step size to 5 minutes. Parameters such as event frequency, number of operation type conversions, and downtime alarm intervals within the window are extracted to generate time series data for the pearlescent material production workshop. The data structure includes fields such as timestamp, event tag, operation category, and operation intensity, which are used for subsequent dynamic trend analysis.

[0065] Data on changes in material production demand in the pearlescent material production workshop were collected based on time-series data.

[0066] In this embodiment of the invention, based on the generated workshop time-series data, the workshop material production demand change data is extracted by comparing the work plan data with the actual material input / running time. The method includes comparing the time between the daily plan and the operation log, the increase or decrease rate of the number of equipment started per unit time, etc., to determine the dynamic evolution process of the actual operating load, which is reflected in the form of data such as the average number of production requests per unit hour, the fluctuation frequency, and the maximum load difference.

[0067] Based on the data on changes in workshop material production demand, a fluctuation chart of workshop production intensity is drawn, and the slope of the increase in workshop operation intensity is calculated based on the fluctuation chart.

[0068] In this embodiment of the invention, the aforementioned material production demand change data is further utilized to plot a workshop production operation intensity fluctuation graph using visualization libraries such as Matplotlib or Plotly. The horizontal axis is set to time, and the vertical axis is set to the total number of started processes or the percentage of running time per unit time. The upward slope of the curve is calculated using a linear fitting algorithm to obtain the numerical value of the upward slope of workshop operation intensity. OLS (least squares) linear fitting is used, and the slopes for different time periods are segmented and statistically analyzed to output important parameters for judging the fatigue growth trend.

[0069] Correlation analysis of equipment operation status was performed based on time-series data from the pearlescent material production workshop to obtain collaborative operation data of workshop equipment.

[0070] In this embodiment of the invention, correlation calculations are performed on the status signals (such as running, standby, and alarm) of key equipment in the time-series data of the pearlescent material production workshop. The Pearson correlation coefficient and mutual information index are used to assess the correlation strength between the operating status sequences of equipment pairs. The analysis objects include reaction vessels, drying systems, transfer pumps, screening equipment, etc. After standardizing their operating timestamp sequences, the synchronization trends between different devices are analyzed to generate workshop equipment collaborative operation data.

[0071] Based on workshop equipment collaborative operation data, determine the risk data of coupling interference between equipment;

[0072] In this embodiment of the invention, based on the collaborative operation data of workshop equipment, mutual interference relationships within high-frequency collaborative groups are identified. A conflict matrix and statistical anomaly detection method are used to identify the abnormal coupling frequency, state switching lag time, and conflict rate between key equipment, extracting coupling interference risk data between equipment. This data forms a risk assessment table with risk level (L1-L5) and frequency score (number of coupling anomalies per hour) as core indicators.

[0073] When the slope of the workshop operation intensity increases by more than 0.87, the dynamic fatigue growth trend of the material production equipment is determined by the data on the risk of coupling interference between equipment.

[0074] In this embodiment of the invention, the obtained workshop operating intensity increase slope value and the equipment coupling interference risk data are jointly judged. When the increase slope value exceeds the set threshold of 0.87 and the corresponding coupling interference risk level is ≥L3, the dynamic fatigue growth trend of the material production equipment is determined to be "growing" according to the logic threshold judgment method, and an evaluation report of this trend is generated as the input for subsequent coupling degradation analysis.

[0075] Please see Figure 3 This is a schematic diagram of the detection of coupling degradation status of production equipment in this invention;

[0076] Preferably, step S2, determining the coupled degradation status of the material production equipment based on the initial property data of the pearlescent raw materials and the dynamic fatigue growth trend of the material production equipment, includes:

[0077] The initial moisture content of the raw materials was measured based on the initial property data of pearlescent raw materials.

[0078] In this embodiment of the invention, the initial moisture content of the raw material is measured based on the moisture sensor readings and the weight difference method results included in the initial property data of the pearlescent raw material. The procedure involves using an infrared moisture analyzer to heat the raw material sample at a constant temperature (set to 120°C for 8 minutes), and calculating the initial moisture content of the raw material as a percentage of mass (%) by combining the mass change of the sample before and after heating. A uniform sample size of 10g is used during the measurement process, and each group is repeated three times before the average value is calculated.

[0079] The particle size distribution of pearlescent raw materials was determined based on the initial property data of the pearlescent raw materials.

[0080] In this embodiment of the invention, a laser particle size analyzer is used to perform high-resolution detection of the particle size of pearlescent raw materials to determine their particle size distribution. The measurement method employs static light scattering, acquiring data on particle signals with scattering angles ranging from 0.02° to 130°. The particle size distribution range is set from 0.1 μm to 100 μm, and the sampling frequency is 1000 times per second. After data acquisition, the D10, D50, and D90 particle size parameters are analyzed using integrated particle size distribution curves to output the pearlescent raw material particle size distribution data.

[0081] Predict the growth trend of viscosity during raw material processing based on the particle size distribution and initial moisture content of pearlescent raw materials;

[0082] In this embodiment of the invention, based on the aforementioned data on the moisture content and particle size distribution of the raw materials, the viscosity growth trend during raw material processing is calculated. A rheometer (shear rate range 0.01 to 100 s⁻¹) is used to test the rheological behavior of the raw material slurry under different moisture content conditions. After the raw materials are prepared into slurries, they are placed on a temperature-controlled (25°C) rheological platform for shear testing. The shear stress-shear rate curves are recorded, and viscosity growth curves are fitted. By comparing the gradients of changes in moisture content and particle size influence factors, the viscosity growth trend during processing is predicted.

[0083] Estimate the increasing trend of stirring resistance in material mixing equipment based on the increasing viscosity trend of raw material processing;

[0084] In this embodiment of the invention, viscosity growth trend data is used to estimate the increasing trend of stirring resistance in the material stirring equipment by calculating the change in the driving force required by the stirring equipment per unit time. This operation is performed by collecting data from the torque sensor on the equipment control panel. A strain gauge torque sensor is installed on the stirring paddle shaft to record the changes in starting torque, stable operating torque, and peak torque during the processing of different batches of materials. After fitting this trend with the viscosity change, the stirring resistance increase curve is obtained.

[0085] Estimate the dynamic fluctuation of the angle of repose of pearlescent raw materials based on the initial property data of pearlescent raw materials;

[0086] In this embodiment of the invention, based on the initial property data of pearlescent raw materials, including particle size, surface charge, and moisture index, the dynamic fluctuation of the angle of repose of the raw materials was measured through a plate tilting experiment. The tilt angle was set to gradually increase from 0° to 60°, and the maximum stable angle under the natural static state of powder accumulation was recorded as the static angle of repose of this batch of raw materials. The experiment was repeated three times under different temperature and humidity environments and particle size treatment conditions to form a data sequence of the fluctuation of the angle of repose of the raw materials.

[0087] Based on the dynamic fluctuation of the angle of repose of pearlescent raw materials and the increasing trend of the stirring resistance of the material mixing equipment, the abnormal shear stress of the detection equipment is detected.

[0088] In this embodiment of the invention, the aforementioned fluctuations in the angle of repose of the raw materials are coupled with the increasing trend of stirring resistance to analyze the shear resistance fluctuation behavior caused by changes in the packing properties of the raw materials and detect abnormal shear stress in the equipment. The abnormality judgment criterion is based on the rate of change of the abrupt change point of the shear resistance curve exceeding a set threshold (Δτ / Δt>3.5Pa / s), which is considered abnormal shear behavior. The data is obtained through real-time synchronous analysis via the equipment torque controller and the PLC acquisition system.

[0089] Based on abnormal shear stress conditions of equipment and the dynamic fatigue growth trend of material production equipment, the growth trend of equipment torque jitter is estimated.

[0090] In this embodiment of the invention, based on the abnormal shear stress and the dynamic fatigue growth trend of the material production equipment, the energy consumption fluctuation and torque instability of the equipment are jointly analyzed to estimate the growth trend of the equipment torque jitter. The analysis method uses FFT (Fast Fourier Transform) spectrum analysis on the torque time series in the historical operating data of the stirring motor to identify the main vibration frequency bands and the growth rate of jitter amplitude, thus obtaining the equipment jitter frequency amplitude curve.

[0091] The coupling degradation status of material production equipment is determined based on the growth trend of equipment torque jitter.

[0092] In this embodiment of the invention, the fluctuation amplitude index (VFI) and its growth slope value in the equipment torque jitter growth trend curve are compared with the equipment fatigue growth trend data. When the VFI growth rate exceeds 0.4 within three cycles and the corresponding fatigue trend level is ≥2, it is comprehensively judged that the material production equipment has entered the enhancement stage of coupled degradation state, and a coupled degradation assessment data report is generated. This data serves as an input reference for subsequent dynamic stability quality monitoring of finished products.

[0093] Preferably, step S2, which involves monitoring the dynamic stability of the finished pearlescent material based on the degradation status of the material production equipment, includes:

[0094] Detecting the imbalance in the coordination of material production equipment based on the coupling degradation status of material production equipment;

[0095] In this embodiment of the invention, the coordination imbalance of material production equipment is detected based on the coupling degradation status of the equipment. This operation is accomplished by collecting real-time operating parameters of multiple key stirring, conveying, and mixing devices, including torque, speed, power, and vibration signals. Using a synchronous data acquisition system, the time series of parameters collected from each device are compared, the correlation coefficient (Pearson correlation coefficient) between the operating parameters of the devices is calculated, and the timing deviation of the device response is detected through time-delay correlation analysis. When the correlation coefficient between devices is lower than 0.85 and the timing deviation exceeds a set threshold (e.g., 500ms), it is determined that the equipment has a coordination imbalance. This detection result is output as the equipment coordination imbalance status data.

[0096] Estimate the abnormal load accumulation of material production equipment based on the imbalance in the coordination of material production equipment.

[0097] In this embodiment of the invention, the load anomaly accumulation status of the material production equipment is estimated based on the imbalance in the coordination of the equipment. Using collected equipment load current data and torque curves, the percentage of time the equipment exceeds the load limit and the magnitude of the exceedance are calculated through integration, generating a load anomaly accumulation curve. Specific indicators of the load anomaly accumulation status include the peak load ratio (actual load / rated load) and the cumulative overload duration. The overload threshold is set at 110% of the rated load, and a cumulative overload duration exceeding 30 minutes is considered significant load anomaly accumulation. This load anomaly accumulation curve provides a basis for subsequent frequency drift detection.

[0098] Detection of production equipment operating frequency drift based on the cumulative abnormal load of production equipment;

[0099] In this embodiment of the invention, based on the accumulated abnormal load of the production equipment, a high-precision spindle speed sensor is used to continuously collect the real-time speed of the production equipment. The sensor's installation position ensures accurate capture of the spindle speed signal, and the data acquisition frequency is set to at least 100 times per second to ensure that subtle fluctuations in speed are completely recorded. The collected real-time speed data undergoes preprocessing, including noise reduction filtering and outlier removal, to ensure the data quality for subsequent analysis. The average speed value of the equipment during normal operation is calculated, and this average value is obtained through historical operating data statistics as a benchmark reference. Then, for the speed data collected every second, the deviation rate from the average speed is calculated. The deviation rate is expressed as a percentage to quantify the instantaneous speed fluctuation amplitude. To more comprehensively analyze the frequency drift characteristics of the equipment speed, the collected speed time series data undergoes discrete Fourier transform processing to convert the time-domain signal to the frequency domain, extract frequency components, and identify the frequency drift amplitude and its changing trend. The frequency drift detection threshold is set to ±0.5 Hz. If the frequency drift amplitude exceeds this threshold and lasts for more than 5 minutes within any time period, it is judged as a frequency drift abnormal event. The anomaly determination process is completed automatically, and the frequency status of the equipment is monitored in real time. The frequency drift detection results are summarized to form equipment frequency drift status data, including drift amplitude, duration and abnormal alarm indicators, which serve as an important basis for equipment operation status assessment and subsequent maintenance decisions.

[0100] Estimate the mixed failure of pearlescent materials based on the drift of the operating frequency of production equipment;

[0101] In this embodiment of the invention, the mixing failure of pearlescent materials is estimated based on the frequency drift of the production equipment. Mixing failure refers to abnormal particle size distribution and color difference fluctuations caused by uneven mixing of raw materials. By comparing the frequency drift data with the particle size distribution data collected by the raw material particle size sensor in a time-series synchronous manner, the coupling relationship between frequency anomalies and particle size anomalies is analyzed. The criteria for judging particle size anomalies are a D50 particle size change exceeding 10% and a particle size distribution width (D90-D10) change exceeding 15%. Based on the coupling analysis results, the mixing failure rate percentage is calculated.

[0102] Estimate the degree of pearlite particle size shift based on the mixed failure of pearlite materials;

[0103] In this embodiment of the invention, the degree of pearlescent material particle size deviation is estimated based on the failure of pearlescent material mixing. The particle size of the sample is detected using a laser particle size analyzer to quantify the particle size deviation rate. This operation is performed at key processes in the production line (after mixing and before packaging), measuring D10, D50, and D90 indicators, and calculating the deviation ratio of the average particle size relative to the standard value. A particle size deviation exceeding 5% is recorded as an abnormal deviation. The particle size deviation data is used as input for color difference fluctuation assessment.

[0104] The color difference fluctuation of the finished pearlescent material is determined based on the degree of particle size deviation of the pearlescent material.

[0105] In this embodiment of the invention, the color difference fluctuation of the finished pearlescent material is determined based on the degree of particle size offset. A high-precision spectrophotometer is used to measure the color difference of the finished pearlescent material samples. The measurement process is conducted under constant temperature and humidity conditions, with the temperature controlled at 23±1°C and the humidity at 50±5%RH to ensure the stability and repeatability of the measurement data. The spectrophotometer measures the reflectance spectrum of the sample and converts the spectral data into internationally recognized CIELAB color space parameters, including the luminance value L*, red-green coordinate a, and yellow-blue coordinate b. This color space can objectively reflect the differences in color perception by the human eye. Multiple measurements are performed on each finished sample to obtain uniformity data, reducing the impact of local color differences on the overall judgment. The measured L*, a*, and b* values ​​are compared with the pre-determined standard sample color values ​​to calculate the color difference value ΔE. The calculation formula adopts the CIEDE2000 standard to ensure the accuracy and scientific nature of the color difference assessment. By comparing color difference data from consecutive batches of finished products, the trend of color difference variation with particle size shift is analyzed. When ΔE exceeds 2, it is judged as abnormal color difference fluctuation, indicating that the color of the finished product changes significantly, affecting visual consistency. Color difference data and particle size shift data are combined, and a correlation is established between the two through statistical analysis methods. This reflects the impact of particle size change on the appearance stability of the finished product. The output color difference fluctuation analysis results serve as an important basis for evaluating the dynamic stability of the finished product, supporting quality control and production process adjustments.

[0106] The dynamic stability of finished pearlescent materials is monitored based on the color difference fluctuation and particle size deviation of the finished pearlescent materials.

[0107] In this embodiment of the invention, the dynamic stability of the finished pearlescent material is monitored based on its color difference fluctuations and particle size shifts. A high-precision colorimeter is used to periodically measure the finished sample to obtain color difference data. This instrument uses a standardized light source and optical sensor to ensure the accuracy and repeatability of the color difference measurement. Simultaneously, a laser particle size analyzer is used to continuously detect the particle size distribution of the finished pearlescent material, obtaining detailed data on the particle size shift, ensuring the timeliness and accuracy of the particle size data. The color difference data and particle size data are processed synchronously in chronological order. A time series analysis method is used to evaluate the dynamic trends of the two types of data. Specifically, a sliding window technique is used to set a fixed-length time window. The window is gradually slid to extract data, and the standard deviations of particle size and color difference within the window are calculated. These standard deviations serve as stability indicators reflecting the fluctuation range of the finished product's particle size distribution and color uniformity. By continuously calculating the stability indicators within the sliding window, a dynamic stability curve is formed, effectively capturing the stable state and abnormal fluctuations of the finished product at different time points. The above analysis results were compiled into a dynamic stability property assessment report. The report details the particle size and color difference fluctuation characteristics of the finished product during the sampling period, including fluctuation amplitude, trend changes, and anomaly identification. The report data is stored in a structured format for later retrieval. This report serves as crucial input data for subsequent steps such as packaging and transportation simulation and quality and safety testing. It provides a basis for accurately simulating material performance changes during packaging and transportation, while also supporting dynamic early warning and adjustment of quality and safety risks. This ensures the accuracy and reliability of the data used in optimizing the pearlescent material production process, achieving closed-loop management of the entire process quality control.

[0108] Preferably, step S3 includes the following steps:

[0109] Step S31: Based on the full-process data of pearlescent material production, simulate the dynamic stability properties of the finished pearlescent material during packaging and transportation to obtain the pearlescent material packaging and transportation simulation data;

[0110] In this embodiment of the invention, data from the entire pearlescent material production process is collected, including key indicators such as finished product particle size distribution, color difference fluctuation, packaging material performance parameters, and packaging sealing status. Finite element analysis (FEA) technology is used to perform mechanical simulation of the packaging structure, simulating the vibration, impact, and pressure distribution generated during transportation. Vibration data is collected from acceleration sensors in the transportation environment, combined with vibration curves from historical logistics paths, to input the actual transportation vibration load into the packaging structure model. Packaging material performance parameters, including elastic modulus, yield strength, and fatigue resistance, are obtained based on laboratory test data. Through numerical simulation, the dynamic response of the packaging structure under stress during transportation is obtained, the stress distribution and deformation at the critical point of packaging damage are calculated, and packaging transportation simulation data is output, including information such as the stress field, deformation field, and damage probability of the packaging structure. This simulation data serves as the basis for subsequent damage prediction.

[0111] Step S32: Based on the simulated data of pearlescent material packaging and transportation, predict the damage to the pearlescent material packaging structure to obtain the damage data of the pearlescent material packaging structure;

[0112] In this embodiment of the invention, stress and deformation data obtained from packaging and transportation simulations are combined with material fatigue life curves to assess fatigue life. Miner's linear cumulative damage theory is used to quantify the fatigue damage of the packaging material, calculating the fatigue damage ratio corresponding to the cumulative stress cycle number and stress amplitude. A fatigue damage ratio threshold (e.g., 0.7) is set to determine the critical state of packaging structure failure. Simultaneously, based on local stress concentration areas in the simulation data, the crack propagation rate is calculated using the stress intensity factor (K) from fracture mechanics, predicting the time and location of crack occurrence. The failure prediction results are output as packaging structure failure probability, failure location, and time points, forming packaging structure failure data. This data provides a direct basis for subsequent monitoring of degradation trends.

[0113] Step S33: Based on the data of damage to the packaging structure of pearlescent materials, monitor the deterioration trend of the finished pearlescent materials according to the dynamic stability properties of the finished pearlescent materials, and obtain the deterioration trend of the finished pearlescent materials.

[0114] In this embodiment of the invention, the impact of packaging damage on the physical environment of the finished product is analyzed by correlating the location of packaging structural damage with the storage location of the finished product. Combined with leakage rate data from the damaged packaging areas, changes in humidity and oxygen content within the finished product are measured, and data are collected in real time using humidity and oxygen sensors. Based on the leakage rate of the damaged packaging and the changing trends of the internal environment of the finished product, the chemical reaction rate and physical change rate of the materials within the finished product are calculated, establishing a deterioration rate model for the finished product. This model, based on the Arrhenius equation and material stability test data, quantitatively describes the deterioration process of the material affected by packaging damage. The deterioration trend data of the pearlescent material is output, represented as a curve of the deterioration index over time, reflecting the trend of decreasing stability of the finished product.

[0115] Step S34: Detect the quality and safety data of pearlescent materials based on the deterioration trend of finished pearlescent materials.

[0116] In this embodiment of the invention, deterioration trend data is compared with quality and safety standards, including material color difference thresholds, particle size change thresholds, and hazardous substance release limits. A multi-index fusion algorithm is used to comprehensively calculate the deterioration index, packaging damage probability, and internal environmental parameters of the finished product, forming a comprehensive quality and safety score. The quality and safety score determines whether the finished product meets quality and safety requirements, outputting pearlescent material quality and safety data. This data serves as a core indicator for quality control, guiding production process optimization and logistics management to ensure finished product quality and safety. A closed-loop transfer of data between each step is achieved; packaging and transportation simulation data provides input for damage prediction; damage data guides deterioration trend monitoring, forming quality and safety data and completing the dynamic monitoring chain.

[0117] Of particular importance, step S32 includes the following steps:

[0118] Step S321: Detect the storage environment data of pearlescent materials based on the simulated data of pearlescent material packaging and transportation;

[0119] In this embodiment of the invention, during the simulation of pearlescent material packaging and transportation, a data simulation system is constructed that includes variables such as transportation cycle, transportation route, temperature and humidity changes, light conditions, vibration frequency, and acceleration to recreate the environmental parameters exposed to the pearlescent material throughout the entire packaging and transportation chain. The time nodes in the transportation simulation data are mapped to geographical locations, and combined with real-time collected environmental monitoring data (including GPS positioning data and environmental sensor data), key environmental indicators such as temperature, humidity, air pressure, and concentration of volatile substances in the air are extracted for the pearlescent material at different stages of the simulation. A multi-channel data acquisition module with GPRS communication function is used to automatically record these parameters, and accuracy is ensured by calibrated sensors (SHT31 for temperature and humidity, and MG811 for gas sensing). Structured processing is used to form the pearlescent material storage environment data, with the data format uniformly in JSON format. The content includes timestamps, geographical locations, temperature values ​​(unit: °C), relative humidity values ​​(unit: %RH), and air pressure values ​​(unit: hPa), which serve as the basic input data for subsequent ultraviolet irradiation intensity analysis and packaging damage prediction.

[0120] Step S322: Detect ultraviolet radiation intensity data of the storage environment based on the storage environment data of pearlescent materials;

[0121] In this embodiment of the invention, the ultraviolet (UV) radiation intensity of the storage area is further correlated with the pearlescent material storage environment data generated in step S321. Specifically, this involves using the latitude and longitude information of the corresponding location in the simulated transportation route to access measured or historical data from a UV irradiation recorder (such as a UV-B recorder MS-212W), and performing data matching processing based on time points and weather conditions. In areas not covered by sensors, weather type and cloud cover level from the environmental data are used as auxiliary variables, and the irradiance conversion formula is used to map weather and time information into estimated UV irradiance values. All data are in W / m² units and arranged chronologically, with one data point per hour. Furthermore, the UV irradiance intensity is integrated to form the cumulative irradiance total for each stage (in J / cm²), reflecting the degree of photoaging affecting the packaging material. The output UV irradiance intensity data of the storage environment is recorded in a time-series structure and stored in a unified database as an important input for subsequent coupled load calculations.

[0122] Step S323: Determine the collision intensity data of pearlescent material during transportation based on the simulation data of pearlescent material packaging and transportation;

[0123] In this embodiment of the invention, collision information is collected at each stage of transportation (such as loading, driving, and unloading) based on simulated data of pearlescent material packaging and transportation. Collision intensity data is obtained by installing a triaxial accelerometer (model ADXL357) and a high-frequency sampling vibration recorder (sampling rate of 1kHz) on the transport vehicle. The data acquisition device is equipped with a threshold alarm mechanism; any axial acceleration exceeding ±10g will trigger a recording marker, forming a high-intensity collision event log. All collision data undergoes vector synthesis calculation, and the RMS acceleration formula is used to analyze sustained impacts. Weighted processing is performed based on vibration duration, frequency, and directionality to output pearlescent material transportation collision intensity data. This data is stored in an event sequence structure, including collision time, impact intensity (in g), impact direction, and duration (in ms), to assess the physical load during transportation.

[0124] Step S324: Determine the pearlescent material packaging coupling load strength data based on the pearlescent material transportation collision strength data and the ultraviolet radiation intensity data of the storage environment;

[0125] In this embodiment of the invention, the ultraviolet irradiation intensity data output in step S322 and the transportation collision intensity data obtained in step S323 are fused and analyzed to construct a calculation model for the coupled load strength of pearlescent material packaging. The coupling logic is based on the stress-strain behavior of the packaging material, with ultraviolet irradiation as the material aging factor and collision intensity as the physical damage factor. According to the weighted scoring mechanism, ultraviolet irradiation and impact acceleration are assigned reduction coefficients (the strength reduction caused by aging is set to 0.2% / MJ·m², and the cumulative impact strength weighting coefficient is 0.5 points / g·time). The data output by calculating the comprehensive load strength value is the coupled load strength data of pearlescent material packaging, with the unit being "remaining percentage of packaging durability". This data is used to characterize the integrity level of the packaging system after the simulation process and serves as a direct input for predicting packaging structure damage.

[0126] Step S325: Based on the coupled load strength data of pearlescent material packaging, predict the structural damage of pearlescent material packaging to obtain the structural damage data of pearlescent material packaging.

[0127] In this embodiment of the invention, based on the packaging coupling load strength data output in step S324, and referring to the fatigue strength critical threshold and fracture life curve of the packaging material obtained from actual testing, the rupture point load and durability parameters of the packaging material (such as polyethylene film, multi-layer cardboard boxes, etc.) under different UV irradiation and impact stress conditions are determined through artificial fatigue testing. When the coupling load strength is lower than the material's tolerance critical value (set as below 30% of the remaining durability), it is predicted to be a high-risk breakage. The breakage probability is statistically analyzed based on historical data, and the breakage data of the pearlescent material packaging structure is output, including the risk level of the breakage location (high, medium, low), the expected breakage time, the packaging layer (outer box, inner film), and the breakage mode (tear, compression deformation, etc.). This data directly serves as a key input for subsequent dynamic stability analysis and quality risk assessment of the finished product.

[0128] Preferably, step S33 includes the following steps:

[0129] Step S331: Estimate the decrease in the sealing performance of the packaging structure based on the damage data of the pearlescent material packaging structure;

[0130] In this embodiment of the invention, damage data of the pearlescent material packaging structure is acquired, including information such as crack size, crack location, and fatigue damage degree. Pressure decay and helium leakage tests are performed on the packaging samples using an airtightness testing instrument. By measuring the rate of change of internal air pressure or the helium leakage rate, and combining this with the packaging structure damage data, the degree of decrease in the packaging structure's airtightness is calculated. Numerical interpolation and regression analysis methods are used to establish a correlation model between crack size and the percentage decrease in airtightness, achieving a quantitative estimation from damage data to changes in airtightness. The numerical value of the decrease in the airtightness of the material packaging structure is output as the basic input for subsequent calculations of the probability of moisture absorption.

[0131] Step S332: Calculate the probability of moisture absorption of pearlescent materials based on the decrease in the sealing performance of the material packaging structure, and obtain the moisture absorption probability data of the pearlescent materials.

[0132] In this embodiment of the invention, based on the decrease in airtightness and external environmental humidity data, the permeation rate of water vapor through the damaged packaging structure is calculated using diffusion transport theory. Darcy's law, combined with the damaged area of ​​the packaging, is used to estimate the increase in internal humidity per unit time. The probability of moisture absorption is calculated by combining a weighted threshold for the finished product's sensitivity to humidity. Probabilistic statistical methods are used to analyze the airtightness and environmental data of multiple batches of packaging samples to obtain a statistically significant distribution of the probability of moisture absorption. The moisture absorption probability data for pearlescent materials is output, clarifying the probability of the finished product being exposed to the risk of moisture absorption.

[0133] Step S333: Determine the oxidation and decomposition trend of the surface coating layer based on the moisture probability data of pearlescent materials;

[0134] In this embodiment of the invention, moisture probability data is combined with the hydrolysis and oxidation reaction kinetic parameters of the finished product's surface coating material. Using the effect curve of moisture on the oxidation rate of the coating obtained from accelerated aging tests, the oxidation decomposition rate under the current moisture probability conditions is derived. By continuously monitoring changes in coating thickness and chemical composition, Fourier transform infrared spectroscopy (FTIR) and scanning electron microscopy (SEM) are used to analyze the decomposition state of the coating. Combined with an oxidation rate model, the oxidation decomposition trend curve of the coating is calculated. The oxidation decomposition trend data is output, providing key parameters for subsequent monitoring of deterioration trends.

[0135] Step S334: Calculate the bacterial infection probability based on the data of damaged packaging structure of pearlescent material and the probability of moisture absorption of pearlescent material to obtain the bacterial infection probability data of pearlescent material;

[0136] In this embodiment of the invention, the conditions for bacterial invasion and reproduction are inferred by combining the environmental exposure caused by packaging damage and the increase in internal humidity. Based on the damaged area and the probability of moisture absorption, a bacterial invasion rate model is established. Combined with a bacterial growth kinetic model, the Monod equation is used to describe the dependence of bacterial growth rate on humidity and temperature. The probability of bacterial infection is calculated using finished product storage environment monitoring data (temperature, humidity) and packaging damage parameters. The model outputs bacterial infection probability data for pearlescent materials by real-time or periodic sampling and culturing to detect bacterial counts, thus characterizing the microbial risk level of the finished product.

[0137] Step S335: Analyze the acid-base change trend based on the bacterial infection probability data of pearlescent materials to obtain the acid-base change trend data of pearlescent materials;

[0138] In this embodiment of the invention, a correlation is established between the probability of bacterial infection and pH changes in the internal environment of the finished product. A high-sensitivity electrochemical pH sensor is placed inside the pearlescent material finished product to collect the pH change curve in real time. The sensor can detect minute pH fluctuations caused by acidic or alkaline metabolites produced during bacterial metabolism. These data are continuously recorded by a data acquisition system to form complete time-series pH change data. Simultaneously, the degree of bacterial infection is determined based on microbial detection data from the surface and interior of the finished product, including indicators such as bacterial species, quantity, and growth rate. Based on the collected pH time-series data and the degree of bacterial infection, a kinetic model of the accumulation of acidic and alkaline substances produced by bacterial metabolism is established. This model mathematically describes the rate of bacterial metabolite production, diffusion, and interaction with the internal environment of the finished product, simulating the accumulation process of acidic and alkaline substances under different bacterial infection levels. Linear regression, nonlinear curve fitting, or machine learning methods are used to analyze the pH change trend over time, determining the quantitative relationship between acid-base changes and the bacterial infection process, and identifying the dynamic characteristics of acid-base changes, such as the rate of change, peak value, and stable range. The output data on acid-base changes not only reflects the impact of bacterial infection on the internal environment of the finished product, but also provides accurate environmental parameters to support the estimation of the degree of subsequent irritant growth, ensuring that the comprehensive assessment of material safety and stability has a scientific data basis, and thus guiding the optimization of production processes and the formulation of quality control measures.

[0139] Step S336: Estimate the degree of irritant growth of pearlescent materials based on the trend data of changes in the acidity and alkalinity of pearlescent materials;

[0140] In this embodiment of the invention, the acid-base changes of the finished pearlescent material are continuously monitored based on the acid-base change trend and the material's irritation response threshold. pH data at different time points are collected to form a complete acid-base change curve. Combined with cytotoxicology experimental data, in vitro cell culture experiments are conducted to determine the cytotoxic response of the material to skin cells and related environmental microorganisms under different acid-base environments, obtaining key indicators such as cell survival rate, cell apoptosis rate, and inflammatory factor release, thus clarifying the irritation threshold and reaction intensity of the material within different pH ranges. Using the quantitative structure-activity relationship (QSAR) method, a mathematical model is constructed to link acid-base values ​​with the irritation index, establishing a functional mapping relationship between acid-base and irritation. The specific process includes selecting an appropriate mathematical model (such as multinomial regression, support vector machine, or neural network), inputting acid-base change data from multiple batches of samples and corresponding cytotoxicology indicators, and obtaining a predictive formula for the acid-base effect on the irritation index after model training and validation. Based on this model, the collected acid-base change trend data are predicted and extrapolated to generate an irritation growth curve for pearlescent materials, dynamically reflecting the irritation changes of the finished product during production and storage. This irritation growth data provides a quantitative basis for the safety assessment of the finished product, helps to warn of potential skin or environmental irritation risks, and guides production adjustments and quality control measures.

[0141] Step S337: Monitor the deterioration trend of the finished pearlescent material based on the degree of irritation growth and the oxidation decomposition trend of the surface coating layer, and obtain the deterioration trend of the finished pearlescent material.

[0142] In this embodiment of the invention, data on the degree of irritation growth and oxidative decomposition trend are fused and analyzed using multiple indicators. A weighted average method or principal component analysis is employed to integrate the two indicators, forming a comprehensive deterioration index. By establishing a correspondence between the deterioration index and actual quality indicators (such as color difference and particle size variation), a dynamic deterioration trend curve is generated. The deterioration trend data of the finished pearlescent material is output, providing a basis for quality and safety control and subsequent production improvements. The data from each of the above steps are interconnected, forming a complete monitoring chain from packaging damage to finished product deterioration, ensuring accurate data transmission and rigorous logic.

[0143] Of particular importance, step S34 includes the following steps:

[0144] Step S341: Estimate the degree of color difference fluctuation of pearlescent materials based on the deterioration trend of finished pearlescent materials;

[0145] In this embodiment of the invention, after collecting data on the degradation trend of the finished pearlescent material, environmental factors closely related to its degradation process, such as humidity fluctuations, oxidation levels, and acid-base changes, are categorized and organized. Combined with accelerated aging simulation experiments, the color difference changes of the material under different environmental conditions are observed. A high-resolution spectrophotometer is used to measure the color difference of multiple batches of finished products in a controlled constant temperature and humidity environment. The lighting conditions are kept constant during the measurement process to eliminate interference from ambient light sources. The color values ​​of each batch at different time points are recorded as time-series data. By comparing the initial color state with the trend of changes over multiple time periods, the growth trend of the color difference value over time is observed. When an accelerated increase in the magnitude of color difference change is detected, this stage is determined to be the stage of enhanced color difference fluctuation. A structured data file containing batch number, measurement time, color difference change magnitude, and fluctuation stage identifier is output as input for subsequent evaluation of the color performance stability of the pearlescent material.

[0146] Step S342: Determine the attenuation of the color rendering ability of the pearlescent material based on the enhancement of color difference fluctuation of the pearlescent material;

[0147] In this embodiment of the invention, the color difference fluctuation enhancement data obtained in the previous step is used as the judgment basis, and the reflectivity of pearlescent materials under specific light source illumination conditions is analyzed. Multi-band spectral reflectance data of the sample is collected using a spectral colorimetric device under standard lighting conditions (e.g., D65 fluorescent lamp), and the intensity changes of the main reflectance peak and the continuity and smoothness of the reflectance spectrum are monitored. If a significant weakening of the main peak's reflectivity is detected, or abnormalities such as deformation or gaps appear in the reflectance spectrum, it is determined that the material's color rendering ability has attenuated. Simultaneously, combined with a manual visual comparison experiment, the sample and a standard color card are compared in color rendering from different viewing angles and backgrounds to verify their differences in visual perception. The output includes: reflectance spectrum change information, color rendering ability attenuation level classification, batch identification, and a traceability path for relevant historical color difference data, forming a dataset on the attenuation of the pearlescent material's color rendering ability.

[0148] Step S343: Estimate the color deviation of the pearlescent material based on the attenuation of its color rendering ability;

[0149] In this embodiment of the invention, based on confirmed color rendering capability attenuation data, the color deviation of pearlescent materials under a natural visual recognition system is further analyzed. Multiple samples are imaged using a high-definition industrial-grade camera in a standardized photographic environment. A constant light source is used to uniformly illuminate the samples, ensuring the consistency and comparability of the image data. After image acquisition, an image analysis device is used to separate the main color region, edge region, and background transition region in the image, and the degree of color shift in the visual channel for each region is calculated. If the color performance difference between the main color region and the edge region exceeds an acceptable threshold, the batch of samples is marked as having abnormal color deviation. The color deviation data includes the visual deviation level, deviation location area, and direction of color tendency change (e.g., cooler, warmer, redder, etc.), and corresponds one-to-one with the color attenuation data from the previous step, used to determine the consistency and trend of color system deviation.

[0150] Step S344: Detect the instability of the optical properties of the pearlescent material based on the color deviation of the pearlescent material;

[0151] In this embodiment of the invention, after obtaining the color deviation status, the optical structure of the pearlescent material is further analyzed to determine whether a systematic instability has occurred. Representative samples are selected, and their particle distribution characteristics are measured using a laser particle size analyzer to observe the concentration and dispersion of particle size. If the sample shows an abnormal increase in particle size or a bimodal distribution, it indicates an imbalance in the particle structure, which will adversely affect the light reflection, refraction, and scattering processes. Simultaneously, a dedicated gloss measuring device is used to measure the gloss of the material surface and track the fluctuations in gloss values ​​with changes in storage period or environmental stress. The abnormal particle size data, abnormal gloss values, and color deviation information are compared and analyzed. When all three are correlated and simultaneously show abnormalities, the material is determined to have entered a state of optical performance instability. The output data includes detailed records such as the unstable batch number, abnormal particle size range, degree of gloss reduction, and deviation correlation items.

[0152] Step S345: Estimate the degradation of the dispersion performance of the pearlescent material based on the deterioration trend of the finished product;

[0153] In this embodiment of the invention, data on key indicators affecting the dispersion performance of pearlescent materials are collected, focusing on the deterioration trend of the materials in the finished product stage. This includes monitoring viscosity changes in the material dispersion, observing particle agglomeration behavior, and measuring surface state changes. Dynamic light scattering tests are performed on the dispersion samples under constant-speed stirring conditions to obtain data on particle size distribution changes and determine whether particle agglomeration or stratification occurs. Simultaneously, a rotational viscometer is used to measure the material's flowability parameters at standard shear rates, and the relationship between these parameters and material deterioration indicators is analyzed. For example, under high temperature and high humidity conditions, if the viscosity continuously increases and the particle distribution exhibits a stratified pattern, this is considered a significant characteristic of dispersion performance degradation. Structured dispersion performance degradation data, including particle distribution shift information, flowability degradation data, and a chain of deterioration influencing factors, is generated to comprehensively assess the material's stability.

[0154] Step S346: Detect the quality and safety data of pearlescent materials based on the degradation of material dispersion performance and the instability of the optical properties of pearlescent materials.

[0155] In this embodiment of the invention, based on the obtained data on dispersion performance degradation and optical performance instability, a comprehensive assessment of the quality and safety status of pearlescent materials is conducted. The two datasets are synchronized over time, and key anomaly indicators, such as particle size fluctuation range, gloss variation trend, and dispersion uniformity level, are extracted. Data labels are established for each batch of samples. By setting a multi-indicator critical threshold system, samples exceeding the range are classified and labeled, for example, as "potential quality risk" or "high instability risk." A unified quality risk level classification table is established, and quality and safety data reports are generated based on parameters such as time, batch, and production line number. The content covers the triggering factors, related indicators, detection time period, and environmental conditions for each anomaly. This data, as a core component of the material production quality and safety database, provides direct data support and evaluation criteria for the traceability system and production process optimization module.

[0156] Preferably, step S4 includes the following steps:

[0157] Step S41: Perform data fusion processing on the quality and safety data of pearlescent materials and the dynamic stability properties of finished pearlescent materials to obtain fluctuation characteristic data of the material production process;

[0158] In this embodiment of the invention, the two types of data are aligned in time and space to ensure consistency of timestamps and matching of sampling granularity. Data preprocessing techniques, such as normalization, are employed to convert quality and safety indicators (e.g., deterioration trends, bacterial infection probabilities, acid-base changes, etc.) and dynamic stability parameters (e.g., particle size shift, color difference fluctuation amplitude, etc.) into a unified numerical range to eliminate dimensional differences. Then, a weighted fusion algorithm is used to set the weights of quality and safety data and dynamic stability data to a fixed ratio determined based on historical production experience and statistical analysis, ensuring a reasonable allocation of their contributions. Key fluctuation characteristics are extracted using multivariate statistical analysis, and time-series analysis is used to detect abnormal fluctuations in the fused data, obtaining fluctuation characteristic data of the material production process. This data reflects the joint fluctuation state of quality and stability during the pearlescent material production process, providing an accurate basis for subsequent full-process traceability.

[0159] Step S42: Perform full-process traceability processing of pearlescent material production based on the fluctuation characteristics data of the material production process to obtain full-process traceability data of pearlescent material production.

[0160] In this embodiment of the invention, the material production process fluctuation characteristic data obtained in step S41 is used to conduct full-process traceability processing for pearlescent material production. The traceability processing constructs a multi-dimensional traceability model based on time series and production nodes, covering the entire production chain from raw material entry, workshop processing, equipment operating status to finished product packaging and transportation. Multi-source data correlation analysis is performed by combining production log data, equipment monitoring data, and quality inspection data, using unique identifiers to link data from different production stages into chains. Data mapping and indexing techniques are applied to construct traceability paths, tracing back anomalies identified in the fluctuation characteristic data to specific processes and equipment operating statuses, generating full-process traceability data for pearlescent material production. This data meticulously records parameter changes and quality and safety status at each production stage, forming comprehensive production quality traceability information.

[0161] Step S43: Evaluate the defect data in the pearlescent material production process based on the traceability data of the entire pearlescent material production process;

[0162] In this embodiment of the invention, a production process defect assessment is conducted based on the traceability data of the entire pearlescent material production process. This assessment compares parameters in historical data templates of the normal production process with those in the current traceability data, using statistical control charts to identify deviations and abnormal segments in the process. The assessment focuses on changes in raw material properties, equipment malfunctions, and fluctuations in process parameters, and quantitatively describes the type, extent, and impact of defects by combining the deviation magnitude of quality and safety indicators. The defect data is output in structured data format, including detailed information such as defect category codes, defect timing, associated equipment, and process nodes. This defect data provides a clear basis for locating risk points and bottlenecks in the production process.

[0163] Step S44: Based on the defect data of the pearlescent material production process, optimize the entire pearlescent material production process data to obtain optimized pearlescent material production process data.

[0164] In this embodiment of the invention, the defect data of the pearlescent material production process obtained in step S43 is used to optimize the entire pearlescent material production process. The optimization process identifies the main influencing factors and their paths of action based on the defect data, and uses causal relationship analysis to clarify the impact weight of each defect parameter on production quality. Subsequently, targeted process parameter adjustment strategies and equipment maintenance plans are formulated to adjust key process parameters such as raw material ratios, processing temperature, and stirring speed, and to optimize equipment operation modes to reduce load fluctuations and coupling degradation. The optimization process employs a closed-loop control system to monitor the implementation effect of optimization measures in real time. Combined with online quality inspection data, the optimization strategy is dynamically adjusted to ensure the effective implementation of optimization measures, generating optimized pearlescent material production process data. This data includes the optimized process parameter set, equipment operation status improvement plans, and quality improvement prediction indicators, serving as an important basis for subsequent production management and quality control.

[0165] This invention also provides a data fusion system for quality and safety traceability in pearlescent material production, used to execute the data fusion method for quality and safety traceability in pearlescent material production as described above. The data fusion system for quality and safety traceability in pearlescent material production includes:

[0166] The raw material initial property determination module is used to acquire data from the entire pearlescent material production process; collect data from the pearlescent material production workshop based on the data from the entire pearlescent material production process; and determine the initial property data of pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the entire pearlescent material production process.

[0167] The finished product dynamic stability monitoring module is used to determine the dynamic fatigue growth trend of the material production equipment based on data from the pearlescent material production workshop; to determine the coupled degradation status of the material production equipment based on the initial property data of the pearlescent raw materials and the dynamic fatigue growth trend of the material production equipment; and to monitor the dynamic stability properties of the finished pearlescent material based on the coupled degradation status of the material production equipment.

[0168] The pearlescent material quality and safety testing module is used to simulate the dynamic stability of finished pearlescent materials based on data from the entire pearlescent material production process, thereby obtaining pearlescent material packaging and transportation simulation data; to monitor the deterioration trend of finished pearlescent materials based on the pearlescent material packaging and transportation simulation data; and to detect the quality and safety data of pearlescent materials based on the deterioration trend of finished pearlescent materials.

[0169] The production process optimization module is used to evaluate the production process defects of pearlescent materials based on the quality and safety data of pearlescent materials and the dynamic stability of finished pearlescent materials; and to optimize the entire production process data of pearlescent materials based on the production process defect data to obtain optimized production process data of pearlescent materials.

[0170] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A data fusion method for quality and safety traceability in pearlescent material production, characterized in that, Includes the following steps: Step S1: Obtain data on the entire pearlescent material production process; collect data from the pearlescent material production workshop based on the data from the entire pearlescent material production process; determine the initial property data of the pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the entire pearlescent material production process. Step S2: Determine the dynamic fatigue growth trend of the material production equipment based on data from the pearlescent material production workshop; this includes: The structural complexity of the pearlescent material production workshop was determined based on data from the workshop. Extract the pearlescent material production workshop operation log from the pearlescent material production workshop data; Time-series analysis was performed on the operation log of the pearlescent material production workshop to obtain time-series data of the pearlescent material production workshop. Data on changes in material production demand in the pearlescent material production workshop were collected based on time-series data. Based on the data on changes in workshop material production demand, a fluctuation chart of workshop production intensity is drawn, and the slope of the increase in workshop operation intensity is calculated based on the fluctuation chart. Correlation analysis of equipment operation status was performed based on time-series data from the pearlescent material production workshop to obtain collaborative operation data of workshop equipment. Based on workshop equipment collaborative operation data, determine the risk data of coupling interference between equipment; When the slope of the workshop operation intensity increases by more than 0.87, the dynamic fatigue growth trend of the material production equipment is determined by the data on the risk of coupling interference between equipment. The coupling degradation status of the material production equipment was determined based on the initial property data of pearlescent raw materials and the dynamic fatigue growth trend of the material production equipment; this included: The initial moisture content of the raw materials was measured based on the initial property data of pearlescent raw materials. The particle size distribution of pearlescent raw materials was determined based on the initial property data of the pearlescent raw materials. Predict the growth trend of viscosity during raw material processing based on the particle size distribution and initial moisture content of pearlescent raw materials; Estimate the increasing trend of stirring resistance in material mixing equipment based on the increasing viscosity trend of raw material processing; Estimate the dynamic fluctuation of the angle of repose of pearlescent raw materials based on the initial property data of pearlescent raw materials; Based on the dynamic fluctuation of the angle of repose of pearlescent raw materials and the increasing trend of the stirring resistance of the material mixing equipment, the abnormal shear stress of the detection equipment is detected. Based on abnormal shear stress conditions of equipment and the dynamic fatigue growth trend of material production equipment, the growth trend of equipment torque jitter is estimated. The coupling degradation status of the material production equipment is determined based on the growth trend of equipment torque jitter; the dynamic stability of the finished pearlescent material is monitored based on the coupling degradation status of the material production equipment. Step S3: Based on the full-process data of pearlescent material production, simulate the packaging and transportation of the finished pearlescent material to obtain the packaging and transportation simulation data; monitor the deterioration trend of the finished pearlescent material based on the packaging and transportation simulation data; and detect the quality and safety data of the finished pearlescent material based on the deterioration trend. Step S4: Based on the quality and safety data of pearlescent materials and the dynamic stability data of finished pearlescent materials, assess the defect data of the pearlescent material production process; based on the defect data of the pearlescent material production process, optimize the production process data of the entire pearlescent material production process to obtain optimized pearlescent material production process data.

2. The data fusion method for quality and safety traceability in pearlescent material production according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Obtain data on the entire pearlescent material production process; Step S12: Collect pearlescent raw material data based on the entire pearlescent material production process; Step S13: Collect data from the pearlescent material production workshop based on the entire pearlescent material production process; Step S14: Determine the initial property data of pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the pearlescent raw materials.

3. The data fusion method for quality and safety traceability in pearlescent material production according to claim 2, characterized in that, Step S14 includes the following steps: Step S141: Detect the impurity content of pearlescent raw materials to obtain impurity content data of pearlescent raw materials; Step S142: Determine the heavy metal content data of pearlescent raw materials based on the impurity content data of the pearlescent raw materials; Step S143: Based on the heavy metal content data of pearlescent raw materials, perform catalytic oxidation analysis on the pearlescent raw material data to obtain the catalytic oxidation status of the pearlescent raw material reaction; Step S144: Detect the surface charge change trend of pearlescent raw materials based on the data of pearlescent raw materials; Step S145: Measure the temperature change trend in the pearlescent material production workshop based on data from the pearlescent material production workshop; Step S146: When the temperature change trend in the pearlescent material production workshop exceeds ±3.2°C, determine the decrease in electrostatic repulsion of raw material particles based on the surface charge change trend of the pearlescent raw materials. Step S147: Estimate the spontaneous agglomeration status of pearlescent raw materials based on the decrease in electrostatic repulsion of raw material particles; Step S148: Determine the initial property data of pearlescent raw materials based on the spontaneous agglomeration status and the catalytic oxidation status of pearlescent raw materials.

4. The data fusion method for quality and safety traceability in pearlescent material production according to claim 1, characterized in that, Step S2, which involves monitoring the dynamic stability of the finished pearlescent material based on the coupling degradation status of the material production equipment, includes: Detecting the imbalance in the coordination of material production equipment based on the coupling degradation status of material production equipment; Estimate the abnormal load accumulation of material production equipment based on the imbalance in the coordination of material production equipment. Detection of production equipment operating frequency drift based on the cumulative abnormal load of production equipment; Estimate the mixed failure of pearlescent materials based on the drift of the operating frequency of production equipment; Estimate the degree of pearlite particle size shift based on the mixed failure of pearlite materials; The color difference fluctuation of the finished pearlescent material is determined based on the degree of particle size deviation of the pearlescent material. The dynamic stability of finished pearlescent materials is monitored based on the color difference fluctuation and particle size deviation of the finished pearlescent materials.

5. The data fusion method for quality and safety traceability in pearlescent material production according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Based on the full-process data of pearlescent material production, simulate the dynamic stability properties of the finished pearlescent material during packaging and transportation to obtain the pearlescent material packaging and transportation simulation data; Step S32: Based on the simulated data of pearlescent material packaging and transportation, predict the damage to the pearlescent material packaging structure to obtain the damage data of the pearlescent material packaging structure; Step S33: Based on the data of damage to the packaging structure of pearlescent materials, monitor the deterioration trend of the finished pearlescent materials according to the dynamic stability properties of the finished pearlescent materials, and obtain the deterioration trend of the finished pearlescent materials. Step S34: Detect the quality and safety data of pearlescent materials based on the deterioration trend of finished pearlescent materials.

6. The data fusion method for quality and safety traceability in pearlescent material production according to claim 5, characterized in that, Step S33 includes the following steps: Step S331: Estimate the decrease in the sealing performance of the packaging structure based on the damage data of the pearlescent material packaging structure; Step S332: Calculate the probability of moisture absorption of pearlescent materials based on the decrease in the sealing performance of the material packaging structure, and obtain the moisture absorption probability data of the pearlescent materials. Step S333: Determine the oxidation and decomposition trend of the surface coating layer based on the moisture probability data of pearlescent materials; Step S334: Calculate the bacterial infection probability based on the data of damaged packaging structure of pearlescent material and the probability of moisture absorption of pearlescent material to obtain the bacterial infection probability data of pearlescent material; Step S335: Analyze the acid-base change trend based on the bacterial infection probability data of pearlescent materials to obtain the acid-base change trend data of pearlescent materials; Step S336: Estimate the degree of irritant growth of pearlescent materials based on the trend data of changes in the acidity and alkalinity of pearlescent materials; Step S337: Monitor the deterioration trend of the finished pearlescent material based on the degree of irritation growth and the oxidation decomposition trend of the surface coating layer, and obtain the deterioration trend of the finished pearlescent material.

7. The data fusion method for quality and safety traceability in pearlescent material production according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Perform data fusion processing on the quality and safety data of pearlescent materials and the dynamic stability properties of finished pearlescent materials to obtain fluctuation characteristic data of the material production process; Step S42: Perform full-process traceability processing of pearlescent material production based on the fluctuation characteristics data of the material production process to obtain full-process traceability data of pearlescent material production. Step S43: Evaluate the defect data in the pearlescent material production process based on the traceability data of the entire pearlescent material production process; Step S44: Based on the defect data of the pearlescent material production process, optimize the entire pearlescent material production process data to obtain optimized pearlescent material production process data.

8. A data fusion system for quality and safety traceability in pearlescent material production, characterized in that, For executing the data fusion method for quality and safety traceability in pearlescent material production as described in claim 1, the data fusion system for quality and safety traceability in pearlescent material production includes: The raw material initial property determination module is used to acquire data from the entire pearlescent material production process; collect data from the pearlescent material production workshop based on the data from the entire pearlescent material production process; and determine the initial property data of pearlescent raw materials based on the data from the pearlescent material production workshop and the data from the entire pearlescent material production process. The finished product dynamic stability monitoring module is used to determine the dynamic fatigue growth trend of the material production equipment based on data from the pearlescent material production workshop; to determine the coupled degradation status of the material production equipment based on the initial property data of the pearlescent raw materials and the dynamic fatigue growth trend of the material production equipment; and to monitor the dynamic stability properties of the finished pearlescent material based on the coupled degradation status of the material production equipment. The pearlescent material quality and safety testing module is used to simulate the dynamic stability of finished pearlescent materials based on data from the entire pearlescent material production process, thereby obtaining pearlescent material packaging and transportation simulation data; to monitor the deterioration trend of finished pearlescent materials based on the pearlescent material packaging and transportation simulation data; and to detect the quality and safety data of pearlescent materials based on the deterioration trend of finished pearlescent materials. The production process optimization module is used to evaluate the production process defects of pearlescent materials based on the quality and safety data of pearlescent materials and the dynamic stability of finished pearlescent materials; and to optimize the entire production process data of pearlescent materials based on the production process defect data to obtain optimized production process data of pearlescent materials.

Images